An ultrasonic image mosaic method based on improved SIFT algorithm

被引：0
|
作者：
Chi, Dazhao [1 ]
Xu, Zhixian [1 ]
Liu, Haichun [2 ]
Li, Qingsheng [2 ]
Guo, Qiang [2 ]
Su, Weigang [2 ]
Jia, Tao [2 ]
机构：
[1] National Key Laboratory of Precision Welding and Joining of Materials and Structures, Harbin Institute of Technology, Harbin,150001, China
[2] PipeChina Engineering Quality Supervision and Inspection Company, Beijing,100013, China
来源：
Hanjie Xuebao/Transactions of the China Welding Institution | 2024年 / 45卷 / 10期
关键词：
A comprehensive non-destructive testing of large structures usually needs a series of C-scans. In order to obtain a panoramic image of the structure under test; the method of sub-image mosaic is studied. According to the dynamic process of ultrasonic imaging and combined with digital image processing technology; an improved image mosaic method for ultrasonic C-scan detection is proposed based on the traditional scale invariant feature transform (SIFT) algorithm. Firstly; in view of the low success rate of ultrasound image registration using the traditional SIFT algorithm; the obtained matching feature points are screened through the vector difference of the starting positions of ultrasonic probe. Secondly; a dynamic programming method is used to find the best stitching path. Finally; a gradual in and out fusion is carried out along the best path for stitching to improve the visual effect of the fused area. Artificial defect contained block and welded piece are prepared and tested. The results of ultrasonic image mosaic show that the improved SIFT algorithm can effectively stitch multiple ultrasonic C-scan sub-images into panoramic images; and the proposed method has high accuracy of feature point matching and small image fusion distortion; which is better than the conventional SIFT image mosaic algorithm. In the mosaic image; the positions of targets match well; which can achieve overall non-destructive evaluation of structural processing quality. © 2024 Harbin Research Institute of Welding. All rights reserved;
D O I：
10.12073/j.hjxb.20240630001
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：1 / 7
相关论文
共 50 条
  • [31] Research on novel optimization SIFT algorithm based fast mosaic method
    Wei, Lisheng
    Zhou, Shengwen
    Communications in Computer and Information Science, 2014, 461 : 23 - 32
  • [32] An Improved Algorithm for Image Mosaic
    Wen, Hongyan
    Zhou, Jianzhong
    ISISE 2008: INTERNATIONAL SYMPOSIUM ON INFORMATION SCIENCE AND ENGINEERING, VOL 1, 2008, : 497 - +
  • [33] Image Mosaic Based on SIFT and Deformation Propagation
    Yao, Li
    2008 IEEE INTERNATIONAL SYMPOSIUM ON KNOWLEDGE ACQUISITION AND MODELING WORKSHOP PROCEEDINGS, VOLS 1 AND 2, 2008, : 848 - 851
  • [34] A Rapid Automatic Image Registration Method Based on Improved SIFT
    Zhu Hongbo
    Xu Xuejun
    Wang Jing
    Chen Xuesong
    Jiang Shaohua
    2011 2ND INTERNATIONAL CONFERENCE ON CHALLENGES IN ENVIRONMENTAL SCIENCE AND COMPUTER ENGINEERING (CESCE 2011), VOL 11, PT A, 2011, 11 : 85 - 91
  • [35] Underwater Image Registrtion With Improved SIFT Algorithm
    Raut, Sukhada
    Pati, Umesh Chandra
    2017 2ND IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT), 2017, : 1237 - 1241
  • [36] A METHOD OF SIFT FEATURE POINTS MATCHING FOR IMAGE MOSAIC
    Zhao, Jie
    Zhou, Hui-Juan
    Men, Guo-Zun
    PROCEEDINGS OF 2009 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-6, 2009, : 2353 - +
  • [37] An image matching method based on improved DCCD and SIFT descriptor
    Department of Geographical Information Science, Nanjing University, Nanjing
    210000, China
    不详
    210000, China
    Wuhan Daxue Xuebao Xinxi Kexue Ban, 12 (1613-1617 and 1645):
  • [38] An improved SIFT algorithm for image stereo matching
    Li, Dan
    Sun, Haitao
    Wang, Haili
    Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University, 2015, 50 (03): : 490 - 496
  • [39] Feature Extraction and Matching of Slam Image Based on Improved SIFT Algorithm
    Mao, Xinrong
    Liu, Kaiming
    Hang, Yanfen
    SSPS 2020: 2020 2ND SYMPOSIUM ON SIGNAL PROCESSING SYSTEMS, 2020, : 18 - 23
  • [40] An improved SIFT algorithm for image registration based realization of the vision figure
    1600, Science and Engineering Research Support Society (09):
12345